HDMNet: A Hierarchical Matching Network with Double Attention for Large-scale Outdoor LiDAR Point Cloud Registration

TL;DR

HDMNet is a hierarchical neural network with double attention designed for efficient and accurate registration of large-scale outdoor LiDAR point clouds, emphasizing local similarity and global matching for improved performance.

Contribution

The paper introduces a novel hierarchical neural network with double attention and a feature consistency enhanced double-soft matching network for large-scale outdoor LiDAR point cloud registration.

Findings

Achieves high registration accuracy on large-scale outdoor LiDAR datasets.

Demonstrates improved efficiency compared to existing methods.

Utilizes a trainable embedding mask to enhance correspondence confidence.

Abstract

Outdoor LiDAR point clouds are typically large-scale and complexly distributed. To achieve efficient and accurate registration, emphasizing the similarity among local regions and prioritizing global local-to-local matching is of utmost importance, subsequent to which accuracy can be enhanced through cost-effective fine registration. In this paper, a novel hierarchical neural network with double attention named HDMNet is proposed for large-scale outdoor LiDAR point cloud registration. Specifically, A novel feature consistency enhanced double-soft matching network is introduced to achieve two-stage matching with high flexibility while enlarging the receptive field with high efficiency in a patch-to patch manner, which significantly improves the registration performance. Moreover, in order to further utilize the sparse matching information from deeper layer, we develop a novel trainable embedding mask to incorporate the confidence scores of correspondences obtained from pose estimation of deeper layer, eliminating additional computations. The high-confidence keypoints in the sparser point cloud of the deeper layer correspond to a high-confidence spatial neighborhood region in shallower layer, which will receive more attention, while the features of non-key regions will be masked. Extensive experiments are conducted on two large-scale outdoor LiDAR point cloud datasets to demonstrate the high accuracy and efficiency of the proposed HDMNet.